eisenjulian

embedding_size = 50
word_embedding_column = tf.feature_column.embedding_column(
    column, dimension=embedding_size)
classifier = tf.estimator.DNNClassifier(
    hidden_units=[100],
    feature_columns=[word_embedding_column], 
    model_dir=os.path.join(model_dir, 'bow_embeddings'))
train_and_evaluate(classifier)

eisenjulian

# Load the tensor with the model weights
weights = classifier.get_variable_value('linear/linear_model/x/weights').flatten()
# Find biggest weights in absolute value
extremes = np.concatenate((sorted_indexes[-8:], sorted_indexes[:8]))
# word_inverted_index is a dictionary that maps from indexes back to tokens
extreme_weights = sorted(
    [(weights[i], word_inverted_index[i]) for i in extremes])
# Create plot
y_pos = np.arange(len(extreme_weights))
plt.bar(y_pos, [pair[0] for pair in extreme_weights], align='center', alpha=0.5)

eisenjulian

def train_and_evaluate(classifier):
    classifier.train(input_fn=train_input_fn, steps=25000)
    eval_results = classifier.evaluate(input_fn=eval_input_fn)
    predictions = np.array([p['logistic'][0] for p in classifier.predict(input_fn=eval_input_fn)])
    tf.reset_default_graph() 
    # Add a PR summary in addition to the summaries that the classifier writes
    pr = summary_lib.pr_curve('precision_recall', predictions=predictions, labels=y_test.astype(bool), num_thresholds=21)
    with tf.Session() as sess:
        writer = tf.summary.FileWriter(os.path.join(classifier.model_dir, 'eval'), sess.graph)
        writer.add_summary(sess.run(pr), global_step=0)

eisenjulian

column = tf.feature_column.categorical_column_with_identity('x', vocab_size)
classifier = tf.estimator.LinearClassifier(
    feature_columns=[column], 
    model_dir=os.path.join(model_dir, 'bow_sparse'))

eisenjulian

x_len_train = np.array([min(len(x), sentence_size) for x in x_train_variable])
x_len_test = np.array([min(len(x), sentence_size) for x in x_test_variable])

def parser(x, length, y):
    features = {"x": x, "len": length}
    return features, y

def train_input_fn():
    dataset = tf.data.Dataset.from_tensor_slices((x_train, x_len_train, y_train))
    dataset = dataset.shuffle(buffer_size=25000)

eisenjulian

vocab_size = 5000
sentence_size = 200
(x_train_variable, y_train), (x_test_variable, y_test) = imdb.load_data(num_words=vocab_size)
x_train = sequence.pad_sequences(
    x_train_variable, 
    maxlen=sentence_size, 
    padding='post', 
    value=0)
x_test = sequence.pad_sequences(
    x_test_variable,

eisenjulian

{
  "expectedInputs": [{
    "possibleIntents": [{
      "inputValueData": {
        "listSelect": {"items": [
          {
            "optionInfo": {
              "synonyms": [],
              "key": "La sentida carta del hijo de Débora Pérez Volpin: \"Tranquila mami, estamos bien y te extrañamos muchísimo\""
            },

eisenjulian

{
  "speech": "Sure!",
  "contextOut": [
    {
      "name": "_actions_on_google_",
      "lifespan": 100,
      "parameters": {}
    }
  ],
  "data": {

eisenjulian

{
  "speech": "The next holiday is in 12 days.\nWhat do you want to do next?",
  "contextOut": [
    {
      "name": "_actions_on_google_",
      "lifespan": 100,
      "parameters": {}
    }
  ],
  "data": {

eisenjulian

curl -X POST -H "Content-Type: application/json" -d '{
  "recipient":{
    "id":"USER_ID"
  },
  "message":{
    "text":"Pick a color:",
    "quick_replies":[
      {
        "content_type":"text",
        "title":"Red",